def test_17_get_abstract_bad_client_id_func(self):
print("Test bad client ID...error expected.")
full_URL = base_plus_endpoint_encoded(
f'/v2/Documents/Abstracts/IFP.017.0240A?similarcount=4')
#response = requests.get(full_URL, headers={})
#r = response.json()
#response_info = r["documents"]["responseInfo"]
#response_set = r["documents"]["responseSet"]
#assert(response_info["count"] == 1)
#print (response_set)
response = requests.get(full_URL, headers=no_client_headers)
r = response.json()
print(r)
#response_info = r["documents"]["responseInfo"]
#response_set = r["documents"]["responseSet"]
assert (response.status_code == 428)
def test_search_advanced6(self):
# query for body summaries or appendixes paragraphs containing "asylum" and "house" within the same paragraph and bring back the document info.
# note this only applies to Freud SE and GW since paragraphs are only indexed within those.
# originally all documents were index that way but now paragraph proximity is simulated via ~25 (within 25 words) instead
# the first part: {!parent which="art_level:1"} tells Solr to only bring back the level 1 info (the document info)
full_URL = base_plus_endpoint_encoded(
'/v2/Database/AdvancedSearch/?advanced_query={!parent which="art_level:1"} parent_tag:(p_body || p_summaries || p_appxs) && para:(asylum house)'
)
response = requests.post(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
#print (r)
response_info = r["documentList"]["responseInfo"]
response_set = r["documentList"]["responseSet"]
assert (response_info["fullCount"] >= 1)
print(response_set[0])
def test_001B_get_embargoed_document(self):
# Try to return current content, should only return abstract
full_URL = base_plus_endpoint_encoded(
f"/v2/Documents/Document/AJP.080.0001A/?return_format=XML")
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
assert (response.ok == True)
r = response.json()
response_info = r["documents"]["responseInfo"]
response_set = r["documents"]["responseSet"]
assert (response_info["count"] == 1)
# should be classified as current content
assert (
response_set[0]["accessLimitedClassifiedAsCurrentContent"] == True)
# we should not have access
assert (response_set[0]["accessLimited"] == True)
def test_002A_get_document_with_hits(self):
# test with real client example
search_param = "?facetfields=art_year_int,art_views_last12mos,art_cited_5,art_authors,art_lang,art_type,art_sourcetype,art_sourcetitleabbr,glossary_group_terms,art_kwds_str&facetlimit=15&facetmincount=1&abstract=true&highlightlimit=5&synonyms=false&fulltext1=Evenly+Suspended+Attention"
search_param_encoded = requests.utils.quote(search_param)
full_URL = base_plus_endpoint_encoded(f"/v2/Documents/Document/PAQ.058.0374A/?return_format=XML&search={search_param_encoded}")
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
assert(response.ok == True)
r = response.json()
response_info = r["documents"]["responseInfo"]
response_set = r["documents"]["responseSet"]
assert(response_info["count"] == 1)
termCount = r["documents"]["responseSet"][0]["termCount"]
term = r["documents"]["responseSet"][0]["term"]
assert(termCount >= 11)
assert (term == "SearchHits(text:(Evenly Suspended Attention))")
def test_13_references_a(self):
"""
Full references
"""
full_URL = base_plus_endpoint_encoded(
'/v2/Database/Search/?smarttext=Goldberg, E.L. Myers, W.A. Zeifman, I. (1974). Some Observations on Three Interracial Analyses. Int. J. Psycho-Anal., 55:495-500.'
)
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
response_info = r["documentList"]["responseInfo"]
response_set = r["documentList"]["responseSet"]
print(f'Smarttext: {response_info["description"]}')
print(response_info["count"])
assert (response_info["count"] == 1)
print(response_set[0])
def test_search_morelike_2a(self):
full_URL = base_plus_endpoint_encoded(
'/v2/Database/MoreLikeThis/?morelikethis=IJP.078.0335A')
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
response_info = r["documentList"]["responseInfo"]
response_set = r["documentList"]["responseSet"]
assert response_info[
"count"] == 1, f"Expected Count == 1, Count: {response_info['count']}"
first_key = list(
response_set[0]["similarityMatch"]["similarDocs"].keys())[0]
length = len(
list(
response_set[0]["similarityMatch"]["similarDocs"].values())[0])
assert length >= 4, f"Expected Values: Count >= 4, First Key: {first_key}, Count: {length}"
def test_1b_facet_art_kwds_multi(self):
# Send a request to the API server and store the response.
full_URL = base_plus_endpoint_encoded(
'/v2/Database/Search/?facetfields=art_kwds_str, art_kwds, terms_highlighted'
)
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
response_info = r["documentList"]["responseInfo"]
print(response_info["facetCounts"]["facet_fields"]["art_kwds_str"])
print(response_info["facetCounts"]["facet_fields"]["art_kwds"])
print(
response_info["facetCounts"]["facet_fields"]["terms_highlighted"])
assert (response_info["fullCount"] >= 135000)
assert (response_info["facetCounts"]["facet_fields"]["art_kwds_str"]
["psychoanalysis"] >= 30)
def test_search_long_para_alt_seems_to_show_solr_misses_one(self):
# This produces 0 results on the GVPi server; this result is correct though
full_URL = base_plus_endpoint_encoded(
'/v2/Database/Search/?sourcecode=AOP&fulltext1="physics%20science%20observations"~90&abstract=True'
)
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
#print (r)
response_info = r["documentList"]["responseInfo"]
response_set = r["documentList"]["responseSet"]
assert (
response_info["count"] == 2
) # should REALLY be 3. I confirmed all three papers above in test_search_long_para...
# not sure why we get 2 here, but set that way for now. TODO
print(response_set)
def test01_sitemapreport(self):
# Login!
sessID, headers, session_info = test_login(
username=localsecrets.PADS_TEST_ID2,
password=localsecrets.PADS_TEST_PW2)
# get temp folder, cross platform
tmpf = tempfile.gettempdir()
# note api_key is required, but already in headers
full_URL = base_plus_endpoint_encoded(
f'/v2/Admin/Sitemap/?size=100&max_records=500&path={tmpf}')
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
# these don't get affected by the level.
r = response.json()
site_map_index = r["siteMapIndex"]
site_map_list = r["siteMapList"]
assert (len(site_map_list) == 5)
def test_001A_get_document_with_hits(self):
# test with real client example
search_param = f"?facetfields=art_year_int,art_views_last12mos,art_cited_5,art_authors,art_lang,art_type,art_sourcetype,art_sourcetitleabbr,glossary_group_terms,art_kwds_str&facetlimit=15&facetmincount=1&highlightlimit=4&synonyms=false&fulltext1={self.search_term}"
search_param_encoded = requests.utils.quote(search_param)
full_URL = base_plus_endpoint_encoded(f"/v2/Documents/Document/IJP.056.0303A/?return_format=XML&search={search_param_encoded}")
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
assert(response.ok == True)
r = response.json()
response_info = r["documents"]["responseInfo"]
response_set = r["documents"]["responseSet"]
assert(response_info["count"] == 1)
termCount = r["documents"]["responseSet"][0]["termCount"]
term = r["documents"]["responseSet"][0]["term"]
print (f"Term: {term} / TermCount: {termCount}")
assert (term == f"SearchHits(text:{self.search_term})")
assert(termCount > 0)
def test_search_morelike_1a(self):
full_URL = base_plus_endpoint_encoded(
'/v2/Database/MoreLikeThis/?morelikethis=AOP.016.0171A&similarcount=4'
)
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
# #print (r)
response_info = r["documentList"]["responseInfo"]
assert (response_info["count"] == 1)
response_set = r["documentList"]["responseSet"]
similar = response_set[0]["similarityMatch"]["similarDocs"][
"AOP.016.0171A"]
for n in similar:
print(n)
print(f"Similar Count: {len(similar)}")
assert (len(similar) == 4)
def test_search_morelike_1a(self):
full_URL = base_plus_endpoint_encoded(
'/v2/Database/Search/?sourcecode=AOP&fulltext1=mind¶scope=dreams&similarcount=4'
)
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
response_info = r["documentList"]["responseInfo"]
response_set = r["documentList"]["responseSet"]
assert response_info[
"count"] >= 15, f"Expected Count >= 15, Count: {response_info['count']}"
first_key = list(
response_set[0]["similarityMatch"]["similarDocs"].keys())[0]
length = len(
list(
response_set[0]["similarityMatch"]["similarDocs"].values())[0])
assert length >= 2, f"Expected Values: Count >= 2, First Key: {first_key}, Count: {length}"
def test_15_get_document_with_similarcount(self):
"""
Since no login or authorization, should just return abstract
"""
full_URL = base_plus_endpoint_encoded(
f'/v2/Documents/Document/JOAP.063.0667A/?search=?journal=&fulltext1=mother love&sort=citeCount&similarcount=2'
)
# local, this works...but fails in the response.py code trying to convert self.status to int.
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
assert (response.ok == True)
r = response.json()
print(r)
response_info = r["documents"]["responseInfo"]
response_set = r["documents"]["responseSet"]
assert (response_info["count"] == 1)
print(response_set)
def test_001D_nonexistent_session(self):
search_param = f"?facetfields=art_year_int,art_views_last12mos,art_cited_5,art_authors,art_lang,art_type,art_sourcetype,art_sourcetitleabbr,glossary_group_terms,art_kwds_str&facetlimit=15&facetmincount=1&highlightlimit=4&synonyms=false&fulltext1={self.search_term}"
search_param_encoded = requests.utils.quote(search_param)
full_URL = base_plus_endpoint_encoded(
f"/v2/Documents/Document/IJP.056.0303A/?return_format=XML&search={search_param_encoded}"
)
headers = {
f"client-session": f"123456789",
"client-id": UNIT_TEST_CLIENT_ID,
"Content-Type": "application/json",
localsecrets.API_KEY_NAME: localsecrets.API_KEY
}
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
print(response.status_code)
assert (response.status_code == 424)
print(response.reason)
assert (response.reason == "Failed Dependency")
def test_v2_get_log_level_1(self):
levels = {
10: "DEBUG",
20: "INFO",
30: "WARNING",
40: "ERROR",
50: "CRITICAL"
}
logger = logging.getLogger() # Get root logger
curr_level = levels.get(logger.level, str(logger.level))
print(curr_level)
# Send a request to the API server and store the response.
full_URL = base_plus_endpoint_encoded(f'/v2/Admin/LogLevel')
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
print(response.status_code)
assert (response.status_code == 405) # rejected
def test_0_most_cited(self):
"""
"""
print(
f"Running: {sys._getframe( ).f_code.co_name} at {datetime.now()}")
full_URL = base_plus_endpoint_encoded('/v2/Database/MostCited/')
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
assert (response.ok == True)
r = response.json()
# print (r)
print(f"Count: {r['documentList']['responseInfo']['count']}")
print(f"Limit: {r['documentList']['responseInfo']['limit']}")
print(
f"ReturnedData: {r['documentList']['responseSet'][0]['stat']['art_cited_5']}"
)
assert (r['documentList']['responseSet'][0]['stat']['art_cited_5'] >=
15)
def test_0a_pads_tests(self):
# Login to PaDS with test account and then check responses to mostCited for access.
if session_id is None:
logger.error(f"PaDS Login error in test")
assert (False)
else:
full_URL = base_plus_endpoint_encoded(
'/v2/Database/MostCited/?limit=10')
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
r = response.json()
print(
f"Count: {r['documentList']['responseInfo']['fullCount']} Count complete: {r['documentList']['responseInfo']['fullCountComplete']}"
)
# PaDS ID provided has peparchive!
# 20211008 Access to items in result list is no longer checked...only when one item is returned.
assert (r['documentList']['responseSet'][0].get(
"accessChecked", None) == False)
def test_0_most_cited_with_similardocs(self):
print(
f"Running: {sys._getframe( ).f_code.co_name} at {datetime.now()}")
full_URL = base_plus_endpoint_encoded(
'/v2/Database/MostCited/?similarcount=3')
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
assert (response.ok == True)
r = response.json()
# print (r)
# see if it can correctly return moreLikeThese
try:
similar_count = int(r['documentList']['responseSet'][0]
['similarityMatch']['similarNumFound'])
except:
similar_count = 0
assert (similar_count >= 1)
def test_1C_meta_contents_for_source(self):
"""
{'infosource': 'volumes_adjacent',
'prev_vol': None,
'matched_vol': {'value': '1', 'count': 34, 'year': '2006'},
'next_vol': {'value': '2', 'count': 39, 'year': 'IJPSP'}}
"""
full_URL = base_plus_endpoint_encoded('/v2/Metadata/Contents/IJPSP/1/?moreinfo=2')
response = requests.get(full_URL, headers=headers)
assert(response.ok == True)
# test return
r = response.json()
print(r['documentList']['responseInfo']['fullCount'])
print(r['documentList']['responseInfo']['supplementalInfo'])
print(r['documentList']['responseInfo']['supplementalInfo']["next_vol"])
assert (r['documentList']['responseInfo']['supplementalInfo']["infosource"] == "volumes_adjacent")
assert (r['documentList']['responseInfo']['supplementalInfo']["prev_vol"] == None)
assert (r['documentList']['responseInfo']['supplementalInfo']["next_vol"] == {'value': '2', 'count': 39})
assert (r['documentList']['responseInfo']['supplementalInfo']["matched_vol"] == {'value': '1', 'count': 34})
def test_1A_meta_contents_for_source(self):
"""
Test with moreinfo == 1 should produce
['documentList']['responseInfo']['supplementalInfo'][infosource] = 'volumes_min_max'
max = 11
min = 1
src_code = 'IJPSP'
"""
full_URL = base_plus_endpoint_encoded('/v2/Metadata/Contents/IJPSP/4/?moreinfo=1')
response = requests.get(full_URL, headers=headers)
assert(response.ok == True)
# test return
r = response.json()
print(r['documentList']['responseInfo']['fullCount'])
print(r['documentList']['responseInfo']['supplementalInfo']["infosource"])
assert (r['documentList']['responseInfo']['supplementalInfo']["infosource"] == "volumes_min_max")
assert (r['documentList']['responseInfo']['supplementalInfo']["min"] == 1)
assert (r['documentList']['responseInfo']['supplementalInfo']["max"] == 11)
assert (r['documentList']['responseInfo']['supplementalInfo']["src_code"] == 'IJPSP')
def test_2_whats_new(self):
"""
(Moved from TestMosts.py)
Set days_back to almost a year to insure current (usually local) database has actually been
updated!
"""
# request login to the API server
full_URL = base_plus_endpoint_encoded(
'/v2/Database/WhatsNew/?days_back=290')
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
assert (response.ok == True)
r = response.json()
response_info = r["whatsNew"]["responseInfo"]
response_set = r["whatsNew"]["responseSet"]
assert (r['whatsNew']['responseInfo']['listType'] == 'newlist')
#assert(r["db_server_ok"] == True)
print(f"Count: {r['whatsNew']['responseInfo']['count']}")
#print (r)
assert (response_info["count"] >= 3)
def test_v2_searchanalysis_author_and_journalcode(self):
full_URL = base_plus_endpoint_encoded(
'/v2/Database/SearchAnalysis/?author=tuckett&sourcecode=AOP')
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
response_info = r["termIndex"]["responseInfo"]
response_set = r["termIndex"]["responseSet"]
print(
f"Term: {response_set[0]['term']} Count: {response_set[0]['termCount']}"
)
term0 = r["termIndex"]["responseSet"][0]["term"]
assert (r["termIndex"]["responseSet"][0]["termCount"] >= 630)
term1 = r["termIndex"]["responseSet"][1]["term"]
print(
f"Term: {response_set[1]['term']} Count: {response_set[1]['termCount']}"
)
assert (r["termIndex"]["responseSet"][1]["termCount"] >= 59)
print(term0)
assert (term0 == '(AOP) (in source)')
def test_1_Download_orig(self):
tempdir = tempfile.gettempdir()
for testArticle in self.testArticlesAllFormats:
print (f"Downloading original formats for: {testArticle}.")
try:
full_URL = base_plus_endpoint_encoded(f'/v2/Documents/Downloads/PDFORIG/{testArticle}/')
response = requests.get(full_URL, headers=headers)
#opener = urllib.request.build_opener()
#headerlist = [(k, v) for k, v in headers.items()]
#opener.addheaders = headerlist
#urllib.request.install_opener(opener)
#fullfilename = os.path.join(tempdir, testArticle + ".orig.pdf")
#response = urllib.request.urlretrieve(full_URL, filename=fullfilename)
# Confirm that the request-response cycle completed successfully.
#assert(response[1]["content-type"] == 'application/pdf')
except Exception as e:
print (f"{testArticle} not available in that format.")
else:
print (f"Downloads complete for {testArticle}.")
def test06_session_log_report_like_pads(self):
# note api_key is required, but already in headers
from datetime import date, timedelta
dt = date.today() - timedelta(14)
print('Current Date :', date.today())
print('14 days before Current Date :', dt)
ts = time.time()
full_URL = base_plus_endpoint_encoded(f'/v2/Admin/Reports/Session-Log?startdate={dt}&limit=100000&offset=0&download=false&sortorder=asc')
response = requests.get(full_URL, headers=headers)
assert(response.ok == True)
print (f"Watched: Admin Report Query Complete. Time={time.time() - ts}")
r = response.json()
response_info = r["report"]["responseInfo"]
response_set = r["report"]["responseSet"]
print (f'Count Retrieved: {response_info["count"]}')
print (f'Fullcount Retrieved: {response_info["fullCount"]}')
if use_server == 5:
assert(response_info["count"] >= 50000)
else:
assert(response_info["count"] >= 100)
def test_0_whats_new(self):
"""
(Moved from TestMosts.py)
"""
# request login to the API server
full_URL = base_plus_endpoint_encoded(
'/v2/Database/WhatsNew/?days_back=30')
response = requests.get(full_URL, headers=headers)
# Confirm that the request-response cycle completed successfully.
assert (response.ok == True)
r = response.json()
response_info = r["whatsNew"]["responseInfo"]
response_set = r["whatsNew"]["responseSet"]
assert (r['whatsNew']['responseInfo']['listType'] == 'newlist')
#assert(r["db_server_ok"] == True)
print(f"{r['whatsNew']['responseInfo']['count']}")
print(r)
if response_info["count"] == 0:
logger.warning("There are no new articles. Could be ok.")
else:
assert (response_info["count"] >= 1)
def test_0_post(self):
"""
"""
# make sure both are not there:
full_URL = base_plus_endpoint_encoded('/v2/Client/Configuration/')
response = requests.delete(full_URL,
headers=headers,
params={'configname': f"{test_config_name_1}, {test_config_name_2}"}
)
# now post the list
response = requests.post(full_URL,
headers=headers,
json=testlist_double)
# Confirm that the request-response cycle completed successfully.
assert(response.ok == True)
assert(response.status_code == 201)
r = response.json()
assert (r == testlist_double)
print ("Post OK: ", r)
def test_v2_searchanalysis_author_and_journalcode_and_text(self):
full_URL = base_plus_endpoint_encoded(
'/v2/Database/SearchAnalysis/?sourcecode=PCT&citecount=3')
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
#print (r)
response_info = r["termIndex"]["responseInfo"]
response_set = r["termIndex"]["responseSet"]
print(
f"Term: {response_set[0]['term']} Count: {response_set[0]['termCount']}"
)
print(
f"Term: {response_set[1]['term']} Count: {response_set[1]['termCount']}"
)
term0 = r["termIndex"]["responseSet"][0]["term"]
assert (term0 == '(PCT) (in source)')
assert (r["termIndex"]["responseSet"][0]["termCount"] == 482)
term1 = r["termIndex"]["responseSet"][1]["term"]
print("Term1=", term1)
assert (term1 == '[3 TO *] (in cited, cited in the last 5 years)')
assert (r["termIndex"]["responseSet"][1]["termCount"] >= 2322)
def test_v2_searchanalysis(self):
full_URL = base_plus_endpoint_encoded(
'/v2/Database/SearchAnalysis/?author=rangell&fulltext1=transference&sourcecode=AOP'
)
response = requests.get(full_URL, headers=headers)
assert (response.ok == True)
r = response.json()
#print (r)
response_info = r["termIndex"]["responseInfo"]
response_set = r["termIndex"]["responseSet"]
print(
f"Term: {response_set[0]['term']} Count: {response_set[0]['termCount']}"
)
assert (response_set[0]["termCount"] >= 38847)
print(
f"Term: {response_set[1]['term']} Count: {response_set[1]['termCount']}"
)
assert (response_set[1]["termCount"] >= 132)
print(
f"Term: {response_set[2]['term']} Count: {response_set[2]['termCount']}"
)
assert (response_set[1]["termCount"] >= 1)
def test_v2_searchanalysis_author_and_journalcode_and_paratext(self):
full_URL = base_plus_endpoint_encoded(
'/v2/Database/SearchAnalysis/?sourcecode=BAP&fulltext1="freud psychoanalysis"~25'
)
response = requests.get(full_URL, headers=headers)
r = response.json()
assert (response.ok == True)
#print (r)
response_info = r["termIndex"]["responseInfo"]
response_set = r["termIndex"]["responseSet"]
print(
f"Term: {response_set[0]['term']} Count: {response_set[0]['termCount']}"
)
print(
f"Term: {response_set[1]['term']} Count: {response_set[1]['termCount']}"
)
term0 = r["termIndex"]["responseSet"][0]["term"]
assert (term0 == '"freud psychoanalysis"~25 (in text)')
assert (r["termIndex"]["responseSet"][0]["termCount"] >= 19000)
term1 = r["termIndex"]["responseSet"][1]["term"]
assert (term1 == '(BAP) (in source)')
assert (r["termIndex"]["responseSet"][1]["termCount"] >= 403)
def test_4_del_and_cleanup(self):
full_URL = base_plus_endpoint_encoded('/v2/Client/Configuration/')
# create test records, if not there
response = requests.put(full_URL,
headers=headers,
json=testlist_double)
# Confirm that the request-response cycle completed successfully.
assert(response.ok == True)
response = requests.delete(full_URL,
headers=headers,
params={'configname': test_config_name_1})
assert(response.ok == True)
r = response.json()
assert (r["configList"][0]["configSettings"] == config_settings_1)
response = requests.delete(full_URL,
headers=headers,
params={'configname': test_config_name_2})
assert(response.ok == True)
r = response.json()
assert (r["configList"][0]["configSettings"] == config_settings_2)
#assert (r == {'configList': [{'configName': test_config_name_2, 'configSettings': config_settings_2}]})
# First create, then delete both at once
response = requests.put(full_URL,
headers=headers,
json=testlist_double)
# Confirm that the request-response cycle completed successfully.
assert(response.ok == True)
print ("Update list in order to test delete, Put OK: ", r)
response = requests.delete(full_URL,
headers=headers,
params={'configname': f"{test_config_name_1}, {test_config_name_2}"}
)
assert(response.ok == True)
r = response.json()
assert (r["configList"][0]["configSettings"] == config_settings_1)
assert (r["configList"][1]["configSettings"] == config_settings_2)
print ("Update list Del OK: ", r)
